Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers

A Claude Code skill + MCP server setup for expert-level Meta Ads campaign analysis. Includes the framework, Learning Phase diagnostics, and 9 reference documents from Meta's official documentation.

Turn any MCP, OpenAPI, or GraphQL server into a CLI — at runtime, with zero codegen

MCP server that enables the use of OpenAI's high-end models and their powerful web search capabilities.

— 优先支持静态分析、dry-run 与本地靶场。exploit、横向移动、持久化、C2、数据外传等高风险能力属于受限实验特性;policy 与 sandbox 元数据不等同于操作系统或容器级隔离。

Demo only. Actual searches run by default (no visible browser). Set SURF_HEADLESS=false to make Chrome visible like in the clip above.

这是基于 everything-claude-code 进行二次开发,提供npm一键安装方式,协议沿用MIT

Each RAG component was sharpened on its own, then folded into one repository: multi-identity auth, observability and systemd supervision come with it.

@cyanheads/git-mcp-server A Git MCP server for AI agents. STDIO & Streamable HTTP. 28 Tools · 1 Resource · 1 Prompt

Automated deep malware reverse engineering driven by AI agents. A Kali-based Docker environment pairs 50+ RE tools with MCP-connected disassembler backends (Binary Ninja or Ghidra) and a structured...

MCP server that gives LLMs access to formal verification via Z3 (SMT solver) and SWI-Prolog (via prolog-wasm-full, includes library(clpfd)), plus tree-sitter-based source code analysis.

AI-native GPU frame debugging for RenderDoc English | 简体中文

A remote MCP server for SubmitMap, a directory of product launch platforms and startup directories.
Agent Skills

Open agent skills for Alpaca's Trading API and Broker API. Each skill is a SKILL.md file with step-by-step instructions your AI coding assistant follows when you ask it to complete a task, such as...

Multi-harness control protocol that turns requests into approved design contracts, orchestrating isolated worker sessions for sequential implementation and independent code reviews under Orca...

Claude Code skill/plugin: Remnawave + Xray Reality/Vision + Caddy selfsteal + mihomo — reference, config generation, diagnostics

provide for AI agents, helping them build complete automated document workflows. Before large-model reasoning begins, ComPDF Skills can handle document parsing, OCR, data extraction, and structured...

AI agents should not give project advice from vibes.

Comprehensive best practices for building applications with the TanStack ecosystem. These skills provide AI coding agents with structured guidelines for TanStack Query, TanStack Router, and TanStack...

Running 5 AI agents in parallel is easy. Making them not break each other's code is the hard part.

SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.

for creating, directing, validating, and delivering image, video, audio, voice, music, 3D, avatar, and interactive media.

A curated list of high-signal resources for (formerly , originally ): frameworks, skills, tooling, deployments, and real-world use cases.

🧠 plan · 🔨 implement · 🔍 review · ✅ QA gate · 🚢 merge Thirty-five agent skills that run a full PR pipeline. Install them into any repo, with any coding agent.

A structured Agent workflow for CUMCM, MCM/ICM, and Diangong Cup — designed to keep a 72–96 hour modeling project coherent from the first decision to the final submission.